Marcelo Grave

According to our database, Marcelo Grave authored at least 12 papers between 2020 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Small Models Exhibit Limited Answer Consistency in Repetition Trials of the Multiple-Choice MMLU-Redux and MedQA Benchmarks.

Claudio S. Pinhanez, Paulo R. Cavalin, Cassia Sampaio Sanctos, Marcelo Carpinette Grave

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

CAT: A Metric-Driven Framework for Analyzing the Consistency-Accuracy Relation of LLMs under Controlled Input Variations.

Paulo Rodrigo Cavalin, Cassia Sampaio Sanctos, Marcelo Grave, Claudio S. Pinhanez, Yago Primerano

CoRR, December, 2025

Exploring Human Perceptions of AI Responses: Insights from a Mixed-Methods Study on Risk Mitigation in Generative Models.

Heloisa Candello, Muneeza Azmat, Uma Sushmitha Gunturi, Raya Horesh, Rogério Abreu de Paula, Heloisa Pimentel, Marcelo Carpinette Grave, Aminat Adebiyi, Tiago Machado, Maysa Malfiza Garcia de Macedo

CoRR, December, 2025

Improving Score Reliability of Multiple Choice Benchmarks with Consistency Evaluation and Altered Answer Choices.

Paulo Rodrigo Cavalin, Cassia Sampaio Sanctos, Marcelo Grave, Claudio S. Pinhanez, Yago Primerano

CoRR, November, 2025

A methodological analysis of prompt perturbations and their effect on attack success rates.

Tiago Machado, Maysa Malfiza Garcia de Macedo, Rogério Abreu de Paula, Marcelo Carpinette Grave, Aminat Adebiyi, Luan Soares de Souza, Enrico Santarelli, Claudio S. Pinhanez

CoRR, November, 2025

The Non-Determinism of Small LLMs: Evidence of Low Answer Consistency in Repetition Trials of Standard Multiple-Choice Benchmarks.

Claudio S. Pinhanez, Paulo R. Cavalin, Cassia Sampaio Sanctos, Marcelo Grave, Yago Primerano

CoRR, September, 2025

A Comprehensive Evaluation framework of Alignment Techniques for LLMs.

Muneeza Azmat, Momin Abbas, Maysa Malfiza Garcia de Macedo, Marcelo Carpinette Grave, Luan Soares de Souza, Tiago Machado, Rogério Abreu de Paula, Raya Horesh, Yixin Chen, Heloisa Caroline de Souza Pereira Candello, Rebecka Nordenlow, Aminat Adebiyi

CoRR, August, 2025

2024

Creating an African American-Sounding TTS: Guidelines, Technical Challenges, and Surprising Evaluations.

Claudio Santos Pinhanez, Raul Fernandez, Marcelo Carpinette Grave, Julio Nogima, Ron Hoory

Proceedings of the 29th International Conference on Intelligent User Interfaces, 2024

2023

"This means nothing to me": Building credibility in conversational systems.

Heloisa Candello, Gabriel Meneguelli Soella, Cassia Sampaio Sanctos, Marcelo Carpinette Grave, Adinan Alves de Brito Filho

Proceedings of the 5th International Conference on Conversational User Interfaces, 2023

2022

How can AI leverage alternative criteria and suggest a better way to measure credit worthiness and economic growth?

Heloisa Candello, Marcelo Grave, Emilio Vital Brazil, Marina Ito, Adinan Alves de Brito Filho, Rogério de Paula

Proceedings of the CUI 2022: 4th Conference on Conversational User Interfaces, Glasgow, United Kingdom, July 26, 2022

2020

Creating Corpora for Seq2Seq Tone Rephrasing Using Social Media Posts.

Paulo R. Cavalin, Marisa Vasconcelos, Marcelo Grave, Claudio S. Pinhanez

Proceedings of the 2020 International Joint Conference on Neural Networks, 2020

From Disjoint Sets to Parallel Data to Train Seq2Seq Models for Sentiment Transfer.

Paulo R. Cavalin, Marisa Vasconcelos, Marcelo Grave, Claudio S. Pinhanez, Victor Henrique Alves Ribeiro

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2020, 2020